If you're lost, start at this blog post.
There are four experts, and each round they compete to get a reward. You get to pick the rewards each round. The Multiplicate Weights Update Algorithm will follow the advice of an expert in each round, and over time try to perform as well as the best expert.
Algorithm state
Experts: | Alice | Bob | Chadwick | Eve |
---|---|---|---|---|
Cumulative rewards: | 0 | 0 | 0 | 0 |
(Normalized) MWUA Weights (?): | ||||
Learning rate (?): | ||||
MWUA cumulative performance |
For round 1, I pick:
Rewards (?)
Experts: | Alice | Bob | Chadwick | Eve |
---|---|---|---|---|
Round 1: |